About: Timemory: Modular Performance Analysis for HPC

Facets (new session)
Description
Metadata
Settings
- owl:sameAs
- Inference Rule:

About: Timemory: Modular Performance Analysis for HPC Goto Sponge NotDistinct Permalink

An Entity of Type : schema:ScholarlyArticle, within Data Space : wasabi.inria.fr associated with source document(s)

Attributes	Values
type	Academic Article research paper schema:ScholarlyArticle
isDefinedBy	Covid-on-the-Web dataset
has title	Timemory: Modular Performance Analysis for HPC
Creator	Awan, Muaaz Brunie, Hugo Deslippe, Jack Gayatri, Rahul Madsen, Jonathan Oliker, Leonid Wang, Yunsong Williams, Samuel Yang, Charlene
Source	PMC
abstract	HPC has undergone a significant transition toward heterogeneous architectures. This transition has introduced several issues in code migration to support multiple frameworks for targeting the various architectures. In order to cope with these challenges, projects such as Kokkos and LLVM create abstractions which map a generic front-end API to the backend that supports the targeted architecture. This paper presents a complementary framework for performance measurement and analysis. Several performance measurement and analysis tools in existence provide their capabilities through various methods but the common theme among these tools are prohibitive limitations in terms of user-level extensions. For this reason, software developers commonly have to learn multiple tools and valuable analysis methods, such as the roofline model, are frequently required to be generated manually. The timemory framework provides complete modularity for performance measurement and analysis and eliminates all restrictions on user-level extensions. The timemory framework also provides a highly-efficient and intuitive method for handling multiple tools/measurements (i.e., “components”) concurrently. The intersection of these characteristics provide ample evidence that timemory can serve as the common interface for existing performance measurement and analysis tools. Timemory components are developed in C++ but includes multi-language support for C, Fortran, and Python codes. Numerous components are provided by the library itself – including, but not limited to, timers, memory usage, hardware counters, and FLOP and instruction roofline models. Additionally, analysis of the intrinsic overhead demonstrates superior performance in comparison with popular tools.
has issue date	2020-05-22(xsd:dateTime)
bibo:doi	10.1007/978-3-030-50743-5_22
has license	no-cc
sha1sum (hex)	e36717fa43f0526de72c47c391f2f320e9629e57
schema:url	https://doi.org/10.1007/978-3-030-50743-5_22
resource representing a document's title	Timemory: Modular Performance Analysis for HPC
has PubMed Central identifier	PMC7295383
schema:publication	High Performance Computing
resource representing a document's body	covid:e36717fa43f0526de72c47c391f2f320e9629e57#body_text
is schema:about of	named entity 'frequently' named entity 'heterogeneous' named entity 'intuitive' named entity 'multiple' named entity 'performance' named entity 'hardware' named entity 'limitations' named entity 'CHALLENGES' named entity 'INCLUDING' named entity 'CHARACTERISTICS' named entity 'order' named entity 'tools' named entity 'common' named entity 'existing' named entity 'timers' named entity 'paper' named entity 'instruction' named entity 'commonly' named entity 'models' named entity 'intersection' named entity 'migration' named entity 'architecture' named entity 'API' named entity 'performance measurement and analysis tools' named entity 'variadic' named entity 'APIs' named entity 'data storage' named entity 'function calls' named entity 'floating-point arithmetic' named entity 'floating-point' named entity 'fork' named entity 'C++' named entity 'inclusive/exclusive' named entity 'source code' named entity 'statically-linked' named entity 'child process' named entity 'GPU' named entity 're-factored' named entity 'run time' named entity 'kernel' named entity 'bandwidth' named entity 'MPI' named entity 'MPI' named entity 'execution model' named entity 'reference counting' named entity 'regex' named entity 'floating-point' named entity 'high-level' named entity 'high-level' named entity 'graph' named entity 'nested hierarchy' named entity '1.2' named entity 'header file' named entity 'abstract objects' named entity 'Linux' named entity 'binary translation' named entity 'member function' named entity 'data type' named entity 'multiply-add' named entity '1.1' named entity 'CPUs' named entity 'built-in' named entity 'input and output' named entity 'NERSC' named entity 'compiler' named entity 'singletons' named entity 'pragmas' named entity 'MPI' named entity 'I/O' named entity 'input parameters' named entity 'OpenMP' named entity 'member functions' named entity 'command-line' named entity 'Geant4' named entity 'virtual functions'

Faceted Search & Find service v1.13.91 as of Mar 24 2020

Alternative Linked Data Documents: Sponger | ODE Content Formats:

RDF

ODATA

Microdata

About

OpenLink Virtuoso version 07.20.3229 as of Jul 10 2020, on Linux (x86_64-pc-linux-gnu), Single-Server Edition (94 GB total memory)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software